NEED: Cross-Subject and Cross-Task Generalization for Video and Image Reconstruction from EEG Signals

Huan Luo (China Three Gorges University) · Shuai Huang (University of Shanghai for Science and Technology) · Haodong Jing (Xi'an Jiaotong University) · Qixian Zhang (Tongji University) · Litao Chang (Shanghai University of Science and Technology) · Yating Feng (Shanghai University of Science and Technology) · Xiao Lin (Shanghai University of Science and Technology) · Chendong Qin (university of shanghai for science and technology) · Han Chen (Tower Research Capital) · Shuwen Jia (Shanghai University of Science and Technology) · Siyi Sun (University of Oxford) · Yongxiong Wang (University of Shanghai for Science and Technology)
brain-computer interfacecross-subject variabilitydual-pathway architectureeeg-based neural decodinghigh-level semanticsindividual adaptation modulelow-level visual dynamicsneural decodingspatial resolutionssimtask specificitytemporal dynamicsunified inference mechanismvideo reconstructionvisual domainszero-shot generalization

Translating brain activity into meaningful visual content has long been recognized as a fundamental challenge in neuroscience and brain-computer interface research. Recent advances in EEG-based neural decoding have shown promise, yet two critical limitations remain in this area: poor generalization across subjects and constraints to specific visual tasks. We introduce NEED, the first unified framework achieving zero-shot cross-subject and cross-task generalization for EEG-based visual reconstruction. Our approach addresses three fundamental challenges: (1) cross-subject variability through an Individual Adaptation Module pretrained on multiple EEG datasets to normalize subject-specific patterns, (2) limited spatial resolution and complex temporal dynamics via a dual-pathway architecture capturing both low-level visual dynamics and high-level semantics, and (3) task specificity constraints through a unified inference mechanism adaptable to different visual domains. For video reconstruction, NEED achieves better performance than existing methods. Importantly, Our model maintains 93.7% of within-subject classification performance and 92.4% of visual reconstruction quality when generalizing to unseen subjects, while achieving an SSIM of 0.352 when transferring directly to static image reconstruction without fine-tuning, demonstrating how neural decoding can move beyond subject and task boundaries toward truly generalizable brain-computer interfaces.